Research-Stack/4-Infrastructure/auto/config/nodes.yaml
allaun 475f6319ea chore(repo): push local 768-commit branch state onto clean remote baseline
This squashes all local history (768 commits) onto the scrubbed PR #90
baseline. Individual commits were lost during filter-repo corruption;
the working tree content is preserved intact.

Build: N/A (working tree state only)
2026-06-15 22:46:50 -05:00

82 lines
2.1 KiB
YAML

# Node inventory — the controller's source of truth.
#
# Tier 1 (always-on): 361395-1, microvm-racknerd, nixos-laptop
# Tier 2 (optional): qfox-1, nixos-steamdeck-1
#
# Tier 1 nodes going down trigger CRITICAL alerts.
# Tier 2 nodes going down are logged as info only.
tier_1_required:
- 361395-1 # self (control plane)
- microvm-racknerd # Caddy reverse proxy, public edge
- nixos-laptop # k3s + Authentik SSO
nodes:
361395-1:
tailscale_ip: 100.72.130.76
hostname: 361395
ssh_target: local
roles: [control-plane, storage]
probes: [system, garage, garage_buckets, usbip]
optional: false
microvm-racknerd:
tailscale_ip: 100.101.247.127
hostname: MicroVM-Racknerd
ssh_target: root@100.101.247.127
roles: [edge, static-files]
probes: [system, caddy, usbip]
optional: false
nixos-laptop:
tailscale_ip: 100.102.173.61
hostname: nixos
ssh_target: root@100.102.173.61
roles: [storage, service-host, compute]
probes: [system, k3s, usbip]
optional: false
qfox-1:
tailscale_ip: 100.88.57.96
hostname: QFox
ssh_target: root@100.88.57.96
roles: [backup, storage, compute]
probes: [system, restic, garage, garage_buckets, gdrive_offload, usbip]
optional: true
nixos-steamdeck-1:
tailscale_ip: 100.85.244.73
hostname: steamdeck
ssh_target: root@100.85.244.73
roles: [compute]
probes: [system, usbip]
optional: true
# --- thresholds ---
thresholds:
disk_warn_pct: 90
memory_warn_pct: 90
cert_min_days: 30
restic_max_age_hours: 28
snapshot_count_warn: 30
garage_nodes_min: 3
# --- alerting ---
alerting:
email:
enabled: true
to: "admin@researchstack.info"
relay_ssh_target: "root@100.101.247.127"
webhook:
enabled: false
url: ""
dashboard:
enabled: false
endpoint: "http://nixos-laptop:30801/api/push/OJm2a1kC3X"
# --- schedule ---
schedule:
node_probes: 300 # seconds between full probe cycles
backup_health: 1800 # seconds between backup checks
cold_copy: 43200 # seconds between cold copy attempts (12h)